© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4029
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets with non-latin characters, especially russian

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     démocr
    -0.68
     jouets
    -0.67
     mères
    -0.66
     réfrig
    -0.65
     cérami
    -0.65
     traités
    -0.64
     blessés
    -0.64
     avoient
    -0.64
     colorés
    -0.64
     présidenti
    -0.63
    POSITIVE LOGITS
     E
    0.33
     right
    0.31
     P
    0.30
     Pues
    0.30
     Sopho
    0.29
     Escribe
    0.29
     Aware
    0.29
     means
    0.28
     near
    0.27
     B
    0.27
    Activations Density 4.409%

    No Known Activations